Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    account
    -0.08
    培养学生
    -0.07
     Saga
    -0.07
     ν
    -0.07
    :false
    -0.07
    券
    -0.07
     Claim
    -0.07
     ar
    -0.07
    .cart
    -0.07
     bastard
    -0.07
    POSITIVE LOGITS
     우리가
    0.07
     buried
    0.07
    ﲪ
    0.06
    抢抓
    0.06
     дома
    0.06
    ynchronize
    0.06
     APS
    0.06
        ↵    ↵    ↵
    0.06
    묄
    0.06
    _dynamic
    0.06
    Act Density 0.001%

    No Known Activations